RichardWooSJTU 283da92bfa fix ep lm head (#3244) ...

Co-authored-by: yuanxiaolan <yuanxiaolan01@baidu.com>

2025-08-12 15:38:28 +08:00

..

attention

[Iluvatar GPU] Optimze attention and moe performance (#3234)

2025-08-08 10:51:24 +08:00

backends

qwen3_moe (#3084)

2025-08-06 14:45:27 +08:00

moe

[V1 Loader] Support DeepSeekV3(bf16) (#3294)

2025-08-11 13:39:28 +08:00

quantization

Move create_parameters to __init__ in FuseMOE for CultassBackend and TritonBackend (#3148)

2025-08-08 15:55:47 +08:00

sample

【Fix】fix mtp bug (#3139)

2025-08-08 13:30:12 +08:00

__init__.py

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

activation.py

native top_p_sampling (#2901)

2025-07-22 14:09:59 +08:00

embeddings.py

[bugfix]fix blockwisefp8 and all_reduce (#3243)

2025-08-06 23:54:33 +08:00

linear.py

[V1 Loader] Support DeepSeekV3(bf16) (#3294)

2025-08-11 13:39:28 +08:00

lm_head.py

fix ep lm head (#3244)

2025-08-12 15:38:28 +08:00

mtp_linear.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

normalization.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

rotary_embedding.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

utils.py

Move create_parameters to __init__ in FuseMOE for CultassBackend and TritonBackend (#3148)

2025-08-08 15:55:47 +08:00